© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 19989
    Prev
    Next
    INDEX
    Explanations

    terms related to clarity and lack of clarity

    oai_token-act-pair · gpt-3.5-turbo

    references to clarity or the lack thereof in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atern
    -0.73
    heimer
    -0.66
    Western
    -0.65
    Il
    -0.64
    ADS
    -0.64
    mine
    -0.63
    Particip
    -0.62
    sites
    -0.62
     Horton
    -0.62
    culture
    -0.61
    POSITIVE LOGITS
     clarity
    1.49
    iness
    0.93
    wcs
    0.82
    20439
    0.81
     clarification
    0.80
     assurance
    0.79
     transparency
    0.78
    mares
    0.76
     clarified
    0.76
    faced
    0.75
    Activations Density 0.005%

    No Known Activations